Knowledge of people's transportation mode is important in many civilian areas, such as urban transportation planning. Current methodologies in collecting travelers' transportation modes are costly and inaccurate. The increasing sensing and computing capabilities of smartphones and their high penetration rate enable automatic transportation mode detection. This paper designs and implements a light-weight and energy-efficient transportation mode detection application only using the accelerometer sensor on smartphones. In this application, we collect accelerometer data in an efficient way and build a convolutional neural network to determine transportation modes. Different architectures and different classification methods are tested within our convolutional neutral networks in our tests and the best combination is selected for this transportation mode detection application. Performance evaluation shows that the proposed convolutional neural network can achieve the highest accuracy in detecting transportation modes.